A Spatial-Temporal Graph Convolutional Networks-based Approach for the OpenPack Challenge 2022

Shurong Chai, Jiaqing Liu, Rahul Kumar Jain, Yinhao Li, Tomoko Tateyama, Yen Wei Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

We report the proposed method of Team Ritsumei for the OpenPack challenge 2022. In this work, we proposed to use a motion-aware and temporal-enhanced Spatial-Temporal Graph Convolutional Networks for the representation of the keypoint modality features. We also leverage the Accelerometer and Gyroscope modality as auxiliary modalities to improve the performance. Our final result is based on the fusion of four modalities. We report the 92.32% F1 score on the submission set, which won the 3rd place in the OpenPack challenge 2022.

Original languageEnglish
Title of host publication2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages267-269
Number of pages3
ISBN (Electronic)9781665453813
DOIs
Publication statusPublished - 2023
Event2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2023 - Atlanta, United States
Duration: 13-03-202317-03-2023

Publication series

Name2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2023

Conference

Conference2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2023
Country/TerritoryUnited States
CityAtlanta
Period13-03-2317-03-23

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems
  • Information Systems and Management
  • Health Informatics
  • Psychology (miscellaneous)

Fingerprint

Dive into the research topics of 'A Spatial-Temporal Graph Convolutional Networks-based Approach for the OpenPack Challenge 2022'. Together they form a unique fingerprint.

Cite this